Episode 15 - Inside the Model Spec

ℹ️ EPISODE INFO

Released

March 25, 2026

Duration

37m

Channel

OpenAI

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

The more AI can do, the more we need to ask what it should and shouldn’t do. In this episode, OpenAI researcher Jason Wolfe joins host Andrew Mayne to talk about the Model Spec, the public framework that defines intended model behavior. They discuss how the Model Spec works in practice, including how the chain of command handles conflicts between instructions, and how OpenAI evolves it based on feedback, real-world use, and new model capabilities. More on our approach to the Model Spec: https://openai.com/index/our-approach-to-the-model-spec/ Chapters 00:00 Introduction 01:10 What is the Model Spec? 03:55 How does the Model Spec work in practice? 06:26 Transparency: Where to read the Model Spec & give feedback 07:51 How did the Model Spec originate? 10:02 How does the spec translate into model behavior? 11:26 What is the hierarchy / chain of command? 13:35 Handling edge cases like Santa Claus 17:41 How does the Model Spec evolve over time? 19:59 What happens when models disagree with the spec? 22:05 How do smaller models follow the spec? 23:16 Is chain-of-thought useful for alignment? 24:16 Model Spec vs Anthropic’s Constitution 26:28 What surprised you most? 26:56 How do you define the scope of the spec? 27:44 What is the future of the Model Spec? 31:16 How should developers think about the spec? 34:44 Asimov’s laws vs Model Spec 37:16 Could AI write a Human Spec?

🎤 SPEAKERS

• Andrew Mayne

  host

  Host of the OpenAI Podcast who interviews guests about AI research and product topics.

• Jason Wolfe

  guest

  OpenAI alignment researcher who helped write the Model Spec and works on spec evaluations and compliance.

🧾 EPISODE SUMMARY

In this episode of OpenAI, featuring Andrew Mayne and Jason Wolfe, Episode 15 - Inside the Model Spec explores openAI’s Model Spec: transparency, policy hierarchy, and alignment practice today The Model Spec is a human-readable, public document describing OpenAI’s intended model behavior, not a guarantee that models perfectly comply today or a full description of the entire ChatGPT system.

🔗 RELATED EPISODES

Why AI needs a new kind of supercomputer network — the OpenAI Podcast Ep. 18

What happens now that AI is good at math? — the OpenAI Podcast Ep. 17

Sam Altman on AGI, GPT-5, and what’s next — the OpenAI Podcast Ep. 1

How AI is accelerating scientific discovery today and what's ahead — the OpenAI Podcast Ep. 10

Inside ChatGPT, AI assistants, and building at OpenAI — the OpenAI Podcast Ep. 2

ChatGPT Atlas and the next era of web browsing — the OpenAI Podcast Ep. 9